INDEX

Explanations

terms related to consumption and consumer behavior

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

er

-0.17

chner

-0.16

iolet

-0.16

ifik

-0.16

ifications

-0.16

Ø¯Ø§Ø±

-0.15

canf

-0.15

Nuitka

-0.15

aments

-0.15

zes

-0.15

POSITIVE LOGITS

ptive

0.41

ption

0.40

ptions

0.35

PTION

0.34

mate

0.32

ables

0.32

pt

0.27

able

0.25

tion

0.24

mates

0.24

Activations Density 0.005%

terms related to consumption and consumer behavior

No Comments

No Known Activations